{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T15:33:52Z","timestamp":1792424032566,"version":"4.5.0"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T00:00:00Z","timestamp":1675123200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["PID2021-126359OB-I00"],"award-info":[{"award-number":["PID2021-126359OB-I00"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1016\/j.neunet.2023.01.048","type":"journal-article","created":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T13:45:23Z","timestamp":1675345523000},"page":"318-329","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":63,"special_numbering":"C","title":["CrimeNet: Neural Structured Learning using Vision Transformer for violence detection"],"prefix":"10.1016","volume":"161","author":[{"given":"Fernando J.","family":"Rend\u00f3n-Segador","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4106-6044","authenticated-orcid":false,"given":"Juan A.","family":"\u00c1lvarez-Garc\u00eda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jose L.","family":"Salazar-Gonz\u00e1lez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tatiana","family":"Tommasi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2023.01.048_b1","first-page":"18","article-title":"Buyer beware","volume":"19","author":"Ainsworth","year":"2002","journal-title":"Security Oz"},{"key":"10.1016\/j.neunet.2023.01.048_b2","doi-asserted-by":"crossref","unstructured":"Arnab,\u00a0A., Dehghani,\u00a0M., Heigold,\u00a0G., Sun,\u00a0C., Lu\u010di\u0107,\u00a0M., & Schmid,\u00a0C. (2021). Vivit: A video vision transformer. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 6836\u20136846).","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"10.1016\/j.neunet.2023.01.048_b3","series-title":"International conference on computer analysis of images and patterns","first-page":"332","article-title":"Violence detection in video using computer vision techniques","author":"Bermejo\u00a0Nievas","year":"2011"},{"key":"10.1016\/j.neunet.2023.01.048_b4","doi-asserted-by":"crossref","unstructured":"Bui,\u00a0T. D., Ravi,\u00a0S., & Ramavajjala,\u00a0V. (2018). Neural graph learning: Training neural networks using graphs. In Proceedings of the eleventh ACM International conference on web search and data mining (pp. 64\u201371).","DOI":"10.1145\/3159652.3159731"},{"key":"10.1016\/j.neunet.2023.01.048_b5","article-title":"Contrastive attention for video anomaly detection","author":"Chang","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2023.01.048_b6","doi-asserted-by":"crossref","unstructured":"Charikar,\u00a0M. S. (2002). Similarity estimation techniques from rounding algorithms. In Proceedings of the thiry-fourth annual ACM Symposium on theory of computing (pp. 380\u2013388).","DOI":"10.1145\/509907.509965"},{"key":"10.1016\/j.neunet.2023.01.048_b7","doi-asserted-by":"crossref","unstructured":"Chen,\u00a0Y., Cao,\u00a0Y., Hu,\u00a0H., & Wang,\u00a0L. (2020). Memory enhanced global-local aggregation for video object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10337\u201310346).","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"10.1016\/j.neunet.2023.01.048_b8","series-title":"Weakly and partially supervised learning frameworks for anomaly detection","author":"Degardin","year":"2020"},{"key":"10.1016\/j.neunet.2023.01.048_b9","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.patrec.2021.01.031","article-title":"Iterative weak\/self-supervised classification framework for abnormal events detection","volume":"145","author":"Degardin","year":"2021","journal-title":"Pattern Recognition Letters"},{"key":"10.1016\/j.neunet.2023.01.048_b10","series-title":"2014 International conference on computer vision theory and applications: Vol. 2","first-page":"478","article-title":"Fast violence detection in video","author":"Deniz","year":"2014"},{"key":"10.1016\/j.neunet.2023.01.048_b11","series-title":"International symposium on visual computing","first-page":"551","article-title":"Violence detection in video by using 3D convolutional neural networks","author":"Ding","year":"2014"},{"key":"10.1016\/j.neunet.2023.01.048_b12","unstructured":"Dosovitskiy,\u00a0A., Beyer,\u00a0L., Kolesnikov,\u00a0A., Weissenborn,\u00a0D., Zhai,\u00a0X., Unterthiner,\u00a0T., et al. (2021). An Image is Worth 16\u00a0\u00d7\u00a016 Words: Transformers for Image Recognition at Scale. In International conference on learning representations."},{"issue":"3","key":"10.1016\/j.neunet.2023.01.048_b13","doi-asserted-by":"crossref","first-page":"1344","DOI":"10.3390\/app11031344","article-title":"Anomalous event recognition in videos based on joint learning of motion and appearance with multiple ranking measures","volume":"11","author":"Dubey","year":"2021","journal-title":"Applied Sciences"},{"key":"10.1016\/j.neunet.2023.01.048_b14","series-title":"2019 International conference on control, automation and information sciences","first-page":"1","article-title":"3D ResNet with ranking loss function for abnormal activity detection in videos","author":"Dubey","year":"2019"},{"key":"10.1016\/j.neunet.2023.01.048_b15","series-title":"Scandinavian conference on image analysis","first-page":"363","article-title":"Two-frame motion estimation based on polynomial expansion","author":"Farneb\u00e4ck","year":"2003"},{"key":"10.1016\/j.neunet.2023.01.048_b16","doi-asserted-by":"crossref","unstructured":"Feng,\u00a0J. -C., Hong,\u00a0F. -T., & Zheng,\u00a0W. -S. (2021). MIST: Multiple instance self-training framework for video anomaly detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 14009\u201314018).","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"10.1016\/j.neunet.2023.01.048_b17","doi-asserted-by":"crossref","DOI":"10.1155\/2021\/8517161","article-title":"AGTH-Net: Attention-based graph convolution-guided third-order hourglass network for sports video classification","volume":"2021","author":"Gao","year":"2021","journal-title":"Journal of Healthcare Engineering"},{"key":"10.1016\/j.neunet.2023.01.048_b18","doi-asserted-by":"crossref","unstructured":"Girdhar,\u00a0R., Carreira,\u00a0J., Doersch,\u00a0C., & Zisserman,\u00a0A. (2019). Video action transformer network. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 244\u2013253).","DOI":"10.1109\/CVPR.2019.00033"},{"key":"10.1016\/j.neunet.2023.01.048_b19","unstructured":"Goodfellow,\u00a0I., Shlens,\u00a0J., & Szegedy,\u00a0C. (2015). Explaining and Harnessing Adversarial Examples. In International conference on learning representations. URL http:\/\/arxiv.org\/abs\/1412.6572."},{"key":"10.1016\/j.neunet.2023.01.048_b20","doi-asserted-by":"crossref","unstructured":"Gopalan,\u00a0A., Juan,\u00a0D. -C., Magalhaes,\u00a0C. I., Ferng,\u00a0C. -S., Heydon,\u00a0A., Lu,\u00a0C. -T., et al. (2021). Neural Structured Learning: Training neural networks with structured signals. In Proceedings of the 14th ACM international conference on web search and data mining (pp. 1150\u20131153).","DOI":"10.1145\/3437963.3441666"},{"key":"10.1016\/j.neunet.2023.01.048_b21","series-title":"2012 IEEE computer society conference on computer vision and pattern recognition workshops","first-page":"1","article-title":"Violent flows: Real-time detection of violent crowd behavior","author":"Hassner","year":"2012"},{"key":"10.1016\/j.neunet.2023.01.048_b22","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/j.neunet.2022.04.022","article-title":"Sediment prediction in the great barrier reef using vision transformer with finite element analysis","volume":"152","author":"Jahanbakht","year":"2022","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2023.01.048_b23","doi-asserted-by":"crossref","unstructured":"Jin,\u00a0W., Ma,\u00a0Y., Liu,\u00a0X., Tang,\u00a0X., Wang,\u00a0S., & Tang,\u00a0J. (2020). Graph structure learning for robust graph neural networks. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 66\u201374).","DOI":"10.1145\/3394486.3403049"},{"key":"10.1016\/j.neunet.2023.01.048_b24","doi-asserted-by":"crossref","unstructured":"Juan,\u00a0D. -C., Lu,\u00a0C. -T., Li,\u00a0Z., Peng,\u00a0F., Timofeev,\u00a0A., Chen,\u00a0Y. -T., et al. (2020). Ultra fine-grained image semantic embedding. In Proceedings of the 13th international conference on web search and data mining (pp. 277\u2013285).","DOI":"10.1145\/3336191.3371784"},{"key":"10.1016\/j.neunet.2023.01.048_b25","series-title":"Multiple instance-based video anomaly detection using deep temporal encoding-decoding","author":"Kamoona","year":"2020"},{"issue":"10s","key":"10.1016\/j.neunet.2023.01.048_b26","doi-asserted-by":"crossref","DOI":"10.1145\/3505244","article-title":"Transformers in vision: A survey","volume":"54","author":"Khan","year":"2022","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.neunet.2023.01.048_b27","doi-asserted-by":"crossref","unstructured":"Li,\u00a0X., Chen,\u00a0M., Nie,\u00a0F., & Wang,\u00a0Q. (2017a). A multiview-based parameter free framework for group detection. In Thirty-first AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v31i1.11208"},{"key":"10.1016\/j.neunet.2023.01.048_b28","article-title":"Locality adaptive discriminant analysis","volume":"Vol. 2201","author":"Li","year":"2017"},{"key":"10.1016\/j.neunet.2023.01.048_b29","series-title":"Convtransformer: A convolutional transformer network for video frame synthesis","author":"Liu","year":"2020"},{"key":"10.1016\/j.neunet.2023.01.048_b30","doi-asserted-by":"crossref","first-page":"4505","DOI":"10.1109\/TIP.2021.3072863","article-title":"Localizing anomalies from weakly-labeled videos","volume":"30","author":"Lv","year":"2021","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2023.01.048_b31","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.eswa.2019.02.032","article-title":"A classification method based on optical flow for violence detection","volume":"127","author":"Mahmoodi","year":"2019","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2023.01.048_b32","doi-asserted-by":"crossref","unstructured":"Paul,\u00a0S., & Chen,\u00a0P. -Y. (2022). Vision Transformers are Robust Learners. In AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v36i2.20103"},{"key":"10.1016\/j.neunet.2023.01.048_b33","series-title":"ICASSP 2019-2019 IEEE international conference on acoustics, speech and signal processing","first-page":"2662","article-title":"Detection of real-world fights in surveillance videos","author":"Perez","year":"2019"},{"key":"10.1016\/j.neunet.2023.01.048_b34","series-title":"2020 IEEE international conference on data mining","first-page":"452","article-title":"Adversarial active learning based heterogeneous graph neural network for fake news detection","author":"Ren","year":"2020"},{"issue":"13","key":"10.1016\/j.neunet.2023.01.048_b35","doi-asserted-by":"crossref","first-page":"1601","DOI":"10.3390\/electronics10131601","article-title":"Violencenet: Dense multi-head self-attention with bidirectional convolutional LSTM for detecting violence","volume":"10","author":"Rend\u00f3n-Segador","year":"2021","journal-title":"Electronics"},{"issue":"3","key":"10.1016\/j.neunet.2023.01.048_b36","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2023.01.048_b37","doi-asserted-by":"crossref","unstructured":"Sadeghian,\u00a0A., Alahi,\u00a0A., & Savarese,\u00a0S. (2017). Tracking the untrackable: Learning to track multiple cues with long-term dependencies. In Proceedings of the IEEE international conference on computer vision (pp. 300\u2013311).","DOI":"10.1109\/ICCV.2017.41"},{"key":"10.1016\/j.neunet.2023.01.048_b38","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1016\/j.neunet.2020.09.013","article-title":"Real-time gun detection in CCTV: An open problem","volume":"132","author":"Salazar\u00a0Gonz\u00e1lez","year":"2020","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2023.01.048_b39","doi-asserted-by":"crossref","unstructured":"Shi,\u00a0L., Zhang,\u00a0Y., Cheng,\u00a0J., & Lu,\u00a0H. (2019). Skeleton-based action recognition with directed graph neural networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7912\u20137921).","DOI":"10.1109\/CVPR.2019.00810"},{"key":"10.1016\/j.neunet.2023.01.048_b40","article-title":"How to train your ViT? Data, augmentation, and regularization in vision transformers","author":"Steiner","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"10.1016\/j.neunet.2023.01.048_b41","doi-asserted-by":"crossref","unstructured":"Sultani,\u00a0W., Chen,\u00a0C., & Shah,\u00a0M. (2018). Real-World Anomaly Detection in Surveillance Videos. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00678"},{"key":"10.1016\/j.neunet.2023.01.048_b42","doi-asserted-by":"crossref","unstructured":"Tian,\u00a0Y., Pang,\u00a0G., Chen,\u00a0Y., Singh,\u00a0R., Verjans,\u00a0J. W., & Carneiro,\u00a0G. (2021). Weakly-supervised video anomaly detection with robust temporal feature magnitude learning. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 4975\u20134986).","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"10.1016\/j.neunet.2023.01.048_b43","series-title":"International conference on machine learning","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021"},{"issue":"1","key":"10.1016\/j.neunet.2023.01.048_b44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-021-95947-y","article-title":"Human activity recognition using wearable sensors, discriminant analysis, and long short-term memory-based neural structured learning","volume":"11","author":"Uddin","year":"2021","journal-title":"Scientific Reports"},{"key":"10.1016\/j.neunet.2023.01.048_b45","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"10.1016\/j.neunet.2023.01.048_b46","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.trc.2006.05.006","article-title":"A motion-based image processing system for detecting potentially dangerous situations in underground railway stations","volume":"14","author":"Velastin","year":"2006","journal-title":"Transportation Research Part C (Emerging Technologies)"},{"issue":"11","key":"10.1016\/j.neunet.2023.01.048_b47","doi-asserted-by":"crossref","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","article-title":"Temporal segment networks for action recognition in videos","volume":"41","author":"Wang","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2023.01.048_b48","series-title":"European conference on computer vision","first-page":"322","article-title":"Not only look, but also listen: Learning multimodal violence detection under weak supervision","author":"Wu","year":"2020"},{"key":"10.1016\/j.neunet.2023.01.048_b49","doi-asserted-by":"crossref","unstructured":"Xu,\u00a0T., & Takano,\u00a0W. (2021). Graph stacked hourglass networks for 3D human pose estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16105\u201316114).","DOI":"10.1109\/CVPR46437.2021.01584"},{"key":"10.1016\/j.neunet.2023.01.048_b50","article-title":"Graph neural network and spatiotemporal transformer attention for 3D video object detection from point clouds","author":"Yin","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2023.01.048_b51","unstructured":"Zhang,\u00a0H., Cisse,\u00a0M., Dauphin,\u00a0Y. N., & Lopez-Paz,\u00a0D. (2018). mixup: Beyond Empirical Risk Minimization. In International conference on learning representations."},{"key":"10.1016\/j.neunet.2023.01.048_b52","doi-asserted-by":"crossref","unstructured":"Zhang,\u00a0B. H., Lemoine,\u00a0B., & Mitchell,\u00a0M. (2018). Mitigating unwanted biases with adversarial learning. In Proceedings of the 2018 AAAI\/ACM conference on AI, ethics, and society (pp. 335\u2013340).","DOI":"10.1145\/3278721.3278779"},{"key":"10.1016\/j.neunet.2023.01.048_b53","doi-asserted-by":"crossref","unstructured":"Zhong,\u00a0J. -X., Li,\u00a0N., Kong,\u00a0W., Liu,\u00a0S., Li,\u00a0T. H., & Li,\u00a0G. (2019). Graph convolutional label noise cleaner: Train a plug-and-play action classifier for anomaly detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 1237\u20131246).","DOI":"10.1109\/CVPR.2019.00133"},{"issue":"10","key":"10.1016\/j.neunet.2023.01.048_b54","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0203668","article-title":"Violence detection in surveillance video using low-level features","volume":"13","author":"Zhou","year":"2018","journal-title":"PLoS One"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608023000606?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608023000606?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:11:44Z","timestamp":1760235104000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608023000606"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":54,"alternative-id":["S0893608023000606"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2023.01.048","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2023,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CrimeNet: Neural Structured Learning using Vision Transformer for violence detection","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2023.01.048","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}]}}